## Error in get(paste0(generic, ".", class), envir = get_method_env()) :
## object 'type_sum.accel' not found
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
Frequencies by state
Continental US A11
state_frequencies <- CensusHLA::census_adjusted_nmdp_hla_frequencies_by_state |> dplyr::filter(allele == 'A*11:01')
out_data <- state_frequencies |>
dplyr::ungroup() |>
dplyr::group_by(region, census_region, fips) |>
dplyr::summarize(gf = sum(us_2020_nmdp_gf))
## `summarise()` has grouped output by 'region', 'census_region'. You can override
## using the `.groups` argument.
gg_state <- usmap::plot_usmap(
data = out_data,
regions = "states",
#exclude = c('Alaksa','Hawaii'),
exclude = c('AK', 'HI'),
values = "gf",
color = "black",
linewidth = 0.1
) +
viridis::scale_fill_viridis(option = "plasma", direction = 1)
out_data |>
DT::datatable(
,filter = 'top'
,rownames = FALSE
,extensions = 'Buttons', options = list(
scrollX=TRUE,
pageLength = 10,
dom = 'Bfrtip',
buttons = c('copy', 'csv', 'excel', 'pdf', 'colvis')
)
)
Alaska and Hawaii US A11 frequencies
ak <-
CensusHLA::census_adjusted_nmdp_hla_frequencies_by_county |> dplyr::filter(state == 'Alaska' &
allele == 'A*11:01')
hi <-
CensusHLA::census_adjusted_nmdp_hla_frequencies_by_county |> dplyr::filter(state == 'Hawaii' &
allele == 'A*11:01')
state_county_frequencies <- rbind(ak, hi)
out_data <- state_county_frequencies |>
dplyr::ungroup() |>
dplyr::filter(allele == 'A*11:01') |>
dplyr::group_by(region, state, census_region, county, fips, loci, allele) |>
dplyr::summarize(us_2020_nmdp_gf_sum = sum(us_2020_nmdp_gf)) |>
dplyr::filter(!(is.na(us_2020_nmdp_gf_sum))) |>
# Create a STATEFP and COUNTYFP column by breaking the fips column on the 3rd character to the end
dplyr::mutate(STATEFP = substr(fips, 1, 2),
COUNTYFP = substr(fips, 3, nchar(fips)))
## `summarise()` has grouped output by 'region', 'state', 'census_region',
## 'county', 'fips', 'loci'. You can override using the `.groups` argument.
gg_ak_and_hi <- usmap::plot_usmap(
data = out_data,
regions = "counties",
#exclude = c('Alaksa','Hawaii'),
include = c('AK', 'HI'),
values = "us_2020_nmdp_gf_sum",
color = "black",
linewidth = 0.1
) +
viridis::scale_fill_viridis(option = "plasma", direction = 1)
gg_ak_and_hi
County Maps
## Reading layer `tl_2020_us_county' from data source
## `/tmp/Rtmpt6zK6y/temp_libpath849b767cc9de/CensusHLA/extdata/tiger_2020/county/tl_2020_us_county.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 3234 features and 17 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -179.2311 ymin: -14.60181 xmax: 179.8597 ymax: 71.43979
## Geodetic CRS: NAD83
## Joining with `by = join_by(STATEFP, COUNTYFP)`
## $out_data
## # A tibble: 254 × 26
## # Groups: region, state, census_region, county, fips, loci [254]
## region state census_region county fips loci allele us_2020_nmdp_gf_sum
## <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 us Texas Anderson County, … Ander… 48001 A A*11:… 0.0936
## 2 us Texas Andrews County, T… Andre… 48003 A A*11:… 0.101
## 3 us Texas Angelina County, … Angel… 48005 A A*11:… 0.0976
## 4 us Texas Aransas County, T… Arans… 48007 A A*11:… 0.111
## 5 us Texas Archer County, Te… Arche… 48009 A A*11:… 0.112
## 6 us Texas Armstrong County,… Armst… 48011 A A*11:… 0.113
## 7 us Texas Atascosa County, … Atasc… 48013 A A*11:… 0.0988
## 8 us Texas Austin County, Te… Austi… 48015 A A*11:… 0.102
## 9 us Texas Bailey County, Te… Baile… 48017 A A*11:… 0.0976
## 10 us Texas Bandera County, T… Bande… 48019 A A*11:… 0.110
## # ℹ 244 more rows
## # ℹ 18 more variables: STATEFP <chr>, COUNTYFP <chr>, COUNTYNS <chr>,
## # GEOID <chr>, NAME <chr>, NAMELSAD <chr>, LSAD <chr>, CLASSFP <chr>,
## # MTFCC <chr>, CSAFP <chr>, CBSAFP <chr>, METDIVFP <chr>, FUNCSTAT <chr>,
## # ALAND <dbl>, AWATER <dbl>, INTPTLAT <chr>, INTPTLON <chr>,
## # geometry <MULTIPOLYGON [°]>
##
## $p1
out_data |>
DT::datatable(
,filter = 'top'
,rownames = FALSE
,extensions = 'Buttons', options = list(
scrollX=TRUE,
pageLength = 10,
dom = 'Bfrtip',
buttons = c('copy', 'csv', 'excel', 'pdf', 'colvis')
)
)
H3 Hexagons
MA
## STATE STATEFP STATENS STATE_NAME
## 1 AL 01 1779775 Alabama
## 2 AK 02 1785533 Alaska
## 3 AZ 04 1779777 Arizona
## 4 AR 05 68085 Arkansas
## 5 CA 06 1779778 California
## 6 CO 08 1779779 Colorado
## 7 CT 09 1779780 Connecticut
## 8 DE 10 1779781 Delaware
## 9 DC 11 1702382 District of Columbia
## 10 FL 12 294478 Florida
## 11 GA 13 1705317 Georgia
## 12 HI 15 1779782 Hawaii
## 13 ID 16 1779783 Idaho
## 14 IL 17 1779784 Illinois
## 15 IN 18 448508 Indiana
## 16 IA 19 1779785 Iowa
## 17 KS 20 481813 Kansas
## 18 KY 21 1779786 Kentucky
## 19 LA 22 1629543 Louisiana
## 20 ME 23 1779787 Maine
## 21 MD 24 1714934 Maryland
## 22 MA 25 606926 Massachusetts
## 23 MI 26 1779789 Michigan
## 24 MN 27 662849 Minnesota
## 25 MS 28 1779790 Mississippi
## 26 MO 29 1779791 Missouri
## 27 MT 30 767982 Montana
## 28 NE 31 1779792 Nebraska
## 29 NV 32 1779793 Nevada
## 30 NH 33 1779794 New Hampshire
## 31 NJ 34 1779795 New Jersey
## 32 NM 35 897535 New Mexico
## 33 NY 36 1779796 New York
## 34 NC 37 1027616 North Carolina
## 35 ND 38 1779797 North Dakota
## 36 OH 39 1085497 Ohio
## 37 OK 40 1102857 Oklahoma
## 38 OR 41 1155107 Oregon
## 39 PA 42 1779798 Pennsylvania
## 40 RI 44 1219835 Rhode Island
## 41 SC 45 1779799 South Carolina
## 42 SD 46 1785534 South Dakota
## 43 TN 47 1325873 Tennessee
## 44 TX 48 1779801 Texas
## 45 UT 49 1455989 Utah
## 46 VT 50 1779802 Vermont
## 47 VA 51 1779803 Virginia
## 48 WA 53 1779804 Washington
## 49 WV 54 1779805 West Virginia
## 50 WI 55 1779806 Wisconsin
## 51 WY 56 1779807 Wyoming
## 52 AS 60 1802701 American Samoa
## 53 GU 66 1802705 Guam
## 54 MP 69 1779809 Commonwealth of the Northern Mariana Islands
## 55 PR 72 1779808 Puerto Rico
## 56 UM 74 1878752 U.S. Minor Outlying Islands
## 57 VI 78 1802710 United States Virgin Islands
## INFO [2025-04-22 18:08:23] Working with state: MS
## Adding missing grouping variables: `census_region`
## Reading layer `tl_2020_28_tract' from data source
## `/tmp/Rtmpt6zK6y/temp_libpath849b767cc9de/CensusHLA/extdata/tiger_2020/tract/tl_2020_28_tract.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 878 features and 12 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -91.65501 ymin: 30.13984 xmax: -88.09789 ymax: 34.9961
## Geodetic CRS: NAD83
## INFO [2025-04-22 18:08:29] Working with state: MS
## Data has been transformed to EPSG:4326.
## Warning: st_centroid assumes attributes are constant over geometries
## Data has been transformed to EPSG:4326.
## Joining with `by = join_by(nmdp_race_code)`
Within County
San Francisco, CA
## INFO [2025-04-22 18:08:47] Working with state: CA
## Adding missing grouping variables: `census_region`
## Reading layer `tl_2020_06_tract' from data source
## `/tmp/Rtmpt6zK6y/temp_libpath849b767cc9de/CensusHLA/extdata/tiger_2020/tract/tl_2020_06_tract.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 9129 features and 12 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -124.482 ymin: 32.52883 xmax: -114.1312 ymax: 42.0095
## Geodetic CRS: NAD83
## $out_data
## # A tibble: 241 × 19
## # Groups: region, state, county, tract, tract_name, loci [241]
## region state county tract tract_name loci allele total_2020_pop
## <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 us 06 075 010101 Census Tract 101.01, … A A*11:… 1988
## 2 us 06 075 010102 Census Tract 101.02, … A A*11:… 1974
## 3 us 06 075 010201 Census Tract 102.01, … A A*11:… 2431
## 4 us 06 075 010202 Census Tract 102.02, … A A*11:… 2034
## 5 us 06 075 010300 Census Tract 103, San… A A*11:… 4006
## 6 us 06 075 010401 Census Tract 104.01, … A A*11:… 2189
## 7 us 06 075 010402 Census Tract 104.02, … A A*11:… 2257
## 8 us 06 075 010500 Census Tract 105, San… A A*11:… 3181
## 9 us 06 075 010600 Census Tract 106, San… A A*11:… 3667
## 10 us 06 075 010701 Census Tract 107.01, … A A*11:… 3701
## # ℹ 231 more rows
## # ℹ 11 more variables: us_2020_nmdp_gf_sum <dbl>, GEOID <chr>, NAME <chr>,
## # NAMELSAD <chr>, MTFCC <chr>, FUNCSTAT <chr>, ALAND <dbl>, AWATER <dbl>,
## # INTPTLAT <chr>, INTPTLON <chr>, geometry <MULTIPOLYGON [°]>
##
## $p1
By Cancer Center catchment area
A11
gg_catchment <- plot_delNero2022_catchment_areas(
query_allele = 'A*11:01',
CensusHLA::a11_catchment_summed$sf_tract_centroids_for_all_states_with_catchment_with_us_population_race_code_percentages_by_tract_summed
)
## Warning in layer_sf(geom = GeomSf, data = data, mapping = mapping, stat = stat,
## : Ignoring unknown parameters: `line`
CensusHLA::a11_catchment_summed$sf_tract_centroids_for_all_states_with_catchment_with_us_population_race_code_percentages_by_tract_summed |> dplyr::select(-geometry) |> dplyr::mutate(patient_pop = total_2020_pop * us_2020_nmdp_gf_sum) |> dplyr::arrange(desc(patient_pop)) |> DT::datatable(
,filter = 'top'
,rownames = FALSE
,extensions = 'Buttons', options = list(
scrollX=TRUE,
pageLength = 10,
dom = 'Bfrtip',
buttons = c('copy', 'csv', 'excel', 'pdf', 'colvis')
)
)
## Warning in instance$preRenderHook(instance): It seems your data is too big for
## client-side DataTables. You may consider server-side processing:
## https://rstudio.github.io/DT/server.html
System and Session info
## R version 4.4.1 (2024-06-14)
## Platform: x86_64-pc-linux-gnu
## Running under: Rocky Linux 9.4 (Blue Onyx)
##
## Matrix products: default
## BLAS/LAPACK: FlexiBLAS OPENBLAS-OPENMP; LAPACK version 3.9.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## time zone: UTC
## tzcode source: system (glibc)
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] dplyr_1.1.4 ggplot2_3.5.1 CensusHLA_0.1.0.9000
##
## loaded via a namespace (and not attached):
## [1] gtable_0.3.6 xfun_0.49
## [3] bslib_0.8.0 htmlwidgets_1.6.4
## [5] tigris_2.1 vctrs_0.6.5
## [7] tools_4.4.1 crosstalk_1.2.1
## [9] generics_0.1.3 curl_6.0.1
## [11] tibble_3.2.1 proxy_0.4-27
## [13] pkgconfig_2.0.3 KernSmooth_2.23-26
## [15] desc_1.4.3 uuid_1.2-1
## [17] lifecycle_1.0.4 h3jsr_1.3.1
## [19] compiler_4.4.1 farver_2.1.2
## [21] stringr_1.5.1 textshaping_0.4.1
## [23] munsell_0.5.1 terra_1.8-5
## [25] codetools_0.2-20 htmltools_0.5.8.1
## [27] class_7.3-23 sass_0.4.9
## [29] yaml_2.3.10 tidyr_1.3.1
## [31] pillar_1.10.0 pkgdown_2.1.1
## [33] jquerylib_0.1.4 classInt_0.4-10
## [35] DT_0.33 cachem_1.1.0
## [37] wk_0.9.4 viridis_0.6.5
## [39] tidyselect_1.2.1 digest_0.6.37
## [41] censusapi_0.8.0 stringi_1.8.4
## [43] purrr_1.0.4 sf_1.0-19
## [45] labeling_0.4.3 rnaturalearth_1.0.1
## [47] fastmap_1.2.0 grid_4.4.1
## [49] colorspace_2.1-1 cli_3.6.4
## [51] magrittr_2.0.3 utf8_1.2.4
## [53] e1071_1.7-16 withr_3.0.2
## [55] scales_1.3.0 rappdirs_0.3.3
## [57] lambda.r_1.2.4 rmarkdown_2.29
## [59] httr_1.4.7 gridExtra_2.3
## [61] futile.logger_1.4.3 rnaturalearthhires_1.0.0.9000
## [63] ragg_1.3.3 evaluate_1.0.1
## [65] knitr_1.49 V8_6.0.0
## [67] viridisLite_0.4.2 s2_1.1.7
## [69] futile.options_1.0.1 rlang_1.1.5
## [71] usmap_0.7.1 Rcpp_1.0.13-1
## [73] glue_1.8.0 DBI_1.2.3
## [75] geojsonsf_2.0.3 formatR_1.14
## [77] rstudioapi_0.17.1 usmapdata_0.3.0
## [79] jsonlite_1.8.9 R6_2.5.1
## [81] systemfonts_1.1.0 fs_1.6.5
## [83] units_0.8-5
## sysname
## "Linux"
## release
## "5.14.0-427.22.1.el9_4.x86_64"
## version
## "#1 SMP PREEMPT_DYNAMIC Wed Jun 19 17:35:04 UTC 2024"
## nodename
## "ip-10-110-10-102.us-west-2.compute.internal"
## machine
## "x86_64"
## login
## "unknown"
## user
## "christian.roy"
## effective_user
## "christian.roy"